Within a decade, P2P has proven to be a technology that enables innovative new services and is used by millions of people every day.

Peer-to-peer systems

We present our design and deployment experiences with LiveSky, a commercially deployed hybrid CDN-P2P live streaming system. CDNs and P2P systems are the common techniques used for live streaming, each having its own set of advantages and disadvantages. LiveSky inherits the best of both worlds: the quality control and reliability of a CDN and the inherent scalability of a P2P system. We address several key challenges in the system design and implementation including (a) dynamic resource scaling while guaranteeing stream quality, (b) providing low startup latency, (c) ease of integration with existing CDN infrastructure, and (d) ensuring network-friendliness and upload fairness in the P2P operation. LiveSky has been commercially deployed and used for several large-scale live streaming events serving more than ten million users in China. We evaluate the performance of LiveSky using data from these real-world deployments. Our results indicate that such a hybrid CDN-P2P system provides quality and user performance comparable to a CDN and effectively scales the system capacity when the user volume exceeds the CDN capacity.

https://www3.cs.stonybrook.edu/~vyas/papers/mm12283-yin.pdf

Design and deployment of a hybrid CDN-P2P system for live video streaming: experiences with LiveSky

Quality assurance for measurements in chemistry and the biosciences seems to deal at a first look with questions such as ‘Did we determine the amount of the requested compound (acrylamide, human growth hormone, etc) accurately?’ Why should the stakeholders of this journal reflect on ‘What to measure?’ Remember, most of the measurements are performed in response to a customer demand (which could be also our own scientific curiosity) And quality is about satisfying the customer One may argue that the analyst in the measurement laboratory obtains the specifications for the ‘what to measure’ from his/her customer But according to my experience, even a simple-looking request from a nonmeasurement expert to the analyst that she/he should just perform a ‘routine service’ by analysing a provided sample with respect to pre-specified parameters can turn into a fruitful scientific discussion and collaboration about defining together the analytical problem and designing a measurement strategy which could really answer the original question By that we are focussing on quality, because we ensure the provision of measurement results allowing the customer to take an informed decision We are not just producing measurement data about a sample, which would comply with the stereotype of an analyst as ‘service maid’ to other scientists dealing with the ‘grand challenges’ of society Consequently, delivering measurement results of adequate quality includes also ‘measuring the right target’ Therefore, the first required step to quality is identifying what is the decision-relevant measurand which is— according to ISO Guide 99 (VIM-3)—the ‘quantity intended to be measured’ However, this may not be sufficient for specifying what to measure; as such an ‘intended quantity’ may not be directly accessible by a measurement This is, for example, the case for a measurand ‘mass fraction of total protein in a foodstuff’ Therefore, the next step requires the intellectual contribution of analysts (‘measurement scientists’) in the problem-solving exercise to an even greater extent Namely, one has to specify the (physical, chemical or biological) entity that can represent adequately the identity, sometimes called analyte or target species (here ‘total protein’), of the measurand (here mass fraction of total protein in a foodstuff) in the measurement procedure For example, the nitrogen content in the food sample as measured by using the so-called Kjeldahl method may serve as substituting quantity in the example But this has to be well thought-out throughout the whole measurement process For the latter, various operations from taking the analytical subsample via sample preparation, creating and registering the instrumental signal until delivering the quantitative measurement result have to be considered Otherwise, one may overlook the interference of nitrogen from non-protein sources, such as melamine, in the foodstuff Many chemical or biological measurement procedures include transformations of the analyte, for instance, by derivatisation or fragmentation Consequently, ‘measurement’ in chemistry and the biosciences can usually not be reduced to a simple one-step attribution of a value to the predefined measurand It includes also mastering the changes of identity (chemical nature) for the target species during the whole measurement procedure For instance, getting to know the mass fraction of acrylamide in toasted bread may include the following steps: extraction (accurate knowledge on extraction yield required), bromination (derivatisation yield has to be known), gas chromatography (separation yield has to be checked) and mass spectrometry Calibration H Emons (&) Geel, Belgium e-mail: JRC-IRMM-ACQUAL@eceuropaeu

What to measure

Internet media content delivery started to emerge roughly a decade ago, and it has subsequently had a major impact on network traffic and usage. Although traditional client-server systems were used initially for delivering media content, researchers and practitioners soon realized that peer-to-peer (P2P) systems, due to their self-scaling properties, had the potential to improve scalability compared with traditional client-server architectures. Consequently, various P2P media streaming systems have been deployed successfully, and corresponding theoretical investigations have been performed on such systems. The rapid developments in this field raise the need for up-to-date literature surveys to summarize them. In recent years, numerous technological discoveries have been achieved. The focus of this report is to survey and discuss these new findings, which include new technological developments, as well as new understandings of these developments and of the existing P2P streaming techniques, through both novel modeling methodologies and measurement-based studies.

/pdf/peer-to-peer-media-streaming-insights-and-new-developments-36nlsk14il.pdf

Peer-to-Peer Media Streaming: Insights and New Developments

Large scale, Internet based mobile TV deployment presents both tremendous opportunities and challenges for mobile operators and technology providers. This paper presents a measurement based study on a large scale mobile TV service offering in China. Within the one month measurement period, our dataset captured over 1 million unique mobile devices and more than 49 million video sessions. Analysis showed that mobile viewing patterns are different from that of landline based IPTV and VoD systems. In particular, the average viewing time is significantly shorter, and the channel popularity distribution is more skewed towards top ranked channels than that of landline based systems. For the channel sojourn time, the distribution follows a piecewise model, which combines lognormal and pareto distribution. The lognormal part, which fits the majority of video sessions, more closely resembles the mobile phone call holding time, rather than the power law distribution in the landline IPTV case. In comparing the 3G and WiFi access methods, we found that users exhibit different behaviors when accessing from different networks. In 3G networks, where users are subject to data charge, users tend to have shorter channel sojourn time and prefer lower bit-rate channels. The parameters of the distributions are also different. Understanding these user behaviors and their implications on network traffic are critical for the success of future mobile TV industry.

/pdf/measurement-and-analysis-of-a-large-scale-commercial-mobile-2ixxuc4ydu.pdf

Measurement and analysis of a large scale commercial mobile internet TV system

The peer-to-peer (P2P) based video streaming has emerged as a promising solution for Internet video distribution. Leveraging the resource available at end users, this approach poses great potential to scale in the Internet. We have now seen the commercial P2P streaming systems that are orders of magnitude larger than the earlier academic systems. We believe understanding its basic principles and limitations are important in the design of future systems. The Coolstreaming, first released in summer 2004, arguably represented the first successful large-scale P2P live streaming system. Since then, the system has been significantly modified and commercially launched. This paper takes an inside look at the new Coolstreaming system by exposing its design options and rationale behind them, and examines their implications on streaming performance. Specifically, by leveraging a large set of traces obtained from recent live event broadcast and extensive simulations, we study the workload characteristics, system dynamics, and impact from a variety of system parameters. We demonstrate that there is a highly skewed resource distribution in such systems and the performance is mostly affected by the system dynamics. In addition, we show that there are inherent correlations and fundamental trade-off among different system parameters, which can be further explored to enhance the system performance.

/pdf/inside-the-new-coolstreaming-principles-measurements-and-4cps2izu0x.pdf

G.Y. Keung

Papers

Inside the New Coolstreaming: Principles, Measurements and Performance Implications